Backend Skills

Automates the management of GitHub issues by fetching, fixing, and monitoring PRs using sub-agents for efficient issue resolution.

Routes plain-language requests for various coding agents into OpenClaw ACP runtime sessions or direct acpx-driven sessions.

Enables display of HTML content on OpenClaw-connected nodes, perfect for interactive demos and visualizations.

Facilitates the creation and verification of AI skills using a test-driven development approach for effective documentation.

Creates detailed implementation plans for multi-step tasks, guiding developers through the coding process with clear, actionable steps.

Facilitates the creation of isolated Git worktrees for feature development, ensuring safe directory selection and verification.

Guides the creation of high-quality MCP servers for LLMs, enabling integration with external APIs using Python or TypeScript.

Facilitates comprehensive PDF file operations including reading, merging, splitting, and creating PDFs with advanced features.

Enhances AI learning through instinct-based systems, enabling adaptive skill evolution and confidence scoring.

Covers best practices for designing REST APIs, including resource naming, status codes, and error handling for robust API development.

Provides comprehensive Playwright E2E testing patterns, including Page Object Model and CI/CD integration for stable test suites.

Creates stunning HTML presentations from scratch or converts PowerPoint files, enhancing visual appeal for non-designers.

Ensures code adheres to security best practices, providing a comprehensive checklist for authentication, input validation, and sensitive data handling.

Enforces test-driven development principles with comprehensive test coverage for new features, bug fixes, and code refactoring.

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.